Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    羱
    -0.07
    ᗗ
    -0.07
     zob
    -0.07
    郈
    -0.07
    垿
    -0.07
    ceptar
    -0.07
    /rand
    -0.07
    Regards
    -0.07
     defiance
    -0.07
     disorder
    -0.07
    POSITIVE LOGITS
    防水
    0.07
     Fe
    0.07
     framing
    0.07
    Sil
    0.07
    비
    0.07
    密集
    0.07
     Activ
    0.07
     Paint
    0.07
    $\
    0.07
    톤
    0.06
    Act Density 0.057%

    No Known Activations